AI Automation Engineer, BetterUp

• This role is for a hands-on builder who thrives on creating smarter, more connected systems—someone who can transform manual workflows into intelligent, AI-enabled automations using cutting-edge tools like Model Context Protocol (MCP), Slack workflows, and secure system integrations
• 3–6 years of professional experience in software or systems engineering, with demonstrated ability to own backend services, integrations, or automation workflows with minimal oversight
• Experience integrating AI capabilities into production systems, including orchestrating LLM-powered workflows across APIs, event-driven systems, and internal services
• Hands-on experience designing AI-assisted automations that operate on real business data with appropriate context, permissions, and safeguards
• Familiarity with using LLM providers (e.g., Claude or similar) as part of larger systems rather than standalone chat or prompt-based tools
• Demonstrated experience integrating APIs and building automations across complex SaaS ecosystems
• Proficiency in n8n and Zapier or custom-built orchestration tools
• Hands-on experience building pipelines or automations using MCP, Step Functions, or equivalent event-driven architectures
• Strong scripting or development skills (e.g., Python, ROR or JavaScript) for writing custom connectors or data transformations
• Familiarity with common SaaS platforms including Okta, Jira, Slack, Workday, Google Workspace, FreshService, and their APIs
• Experience working with authentication protocols (e.g., SAML, OAuth), and systems like Okta, GCP, or AWS

Desirable

• We’re looking for an AI Automation and Integration Engineer to join our rapidly evolving IT & AI Workspace Technology team
• You’ll design and implement scalable automations across our SaaS ecosystem, partner closely with our AI product and infrastructure teams, and bring a high degree of technical rigor and curiosity to every problem you solve
• This is a key role on a small, fast-moving team where your work will directly impact how we scale, automate, and future-proof our internal operations
• MCP & AI Workflow Engineering:
• Implement and scale our Model Context Protocol (MCP) to support secure, composable AI workflows across Slack, Jira, Salesforce, GitHub, AWS-based infrastructure, LLM providers (e.g., Claude), and internal APIs
• Design agentic systems that enable AI tooling to integrate seamlessly with operational data and user identity services
• Author requests for comments (RFCs), technical requirements documents (TRDs), and internal documentation to align MCP features with enterprise use cases
• Automation & Integration Development:
• Build and maintain scalable automations and secure APIs to reduce operational overhead in onboarding, provisioning, and data lifecycle management
• Own development and maintenance of reusable modules for identity sync, data uploads (e.g., CSV bulk importers), and AI-to-API orchestration
• Drive continuous improvement across automation platforms by collaborating with stakeholder teams across the business
• Security, Identity & System Governance:
• Work with InfoSec and IT teams to enforce role-based access controls and SAML/SSO integrations
• Harden identity workflows across US and EU regions, ensuring compliance with internal and external standards
• Support audit readiness through traceable change management and data integrity practices
• Cross-Functional Collaboration:
• Attend cross functional standups, Architecture Roundtables, and AI working groups to ensure engineering solutions align with company goals
• Partner closely with stakeholders to balance speed and safety in fast-moving pilot initiatives
• Advocate for test-driven development (TDD), documentation, and open source-inspired code reusability
• What Success Looks Like:
• MCP server scaled and adopted across multiple workflows with stable, secure integrations
• Automation measurably reduced manual data entry through bulk import and automation tooling (e.g., 50% reduction)
• Onboarding and provisioning latency improved through identity automation (e.g., 30% faster completion)
• Clear documentation, playbooks, and dashboards enable stakeholders to self-serve with AI tools and automation templates, not rely on ad-hoc IT custom work
• All automation systems have strong test coverage, robust monitoring, and meet security review requirements, with audit-ready logs for provisioning and data movement
• Impact is visible and quantified through simple time-saved and adoption metrics layered on top of Jira, dashboards, and usage telemetry